seg/trabalho1/afreq.py

import sys
import cesar

if len(sys.argv) < 2:
    print("Usage: python3 afreq.py [arquivo]")
    sys.exit(1)

frequencias = {
    'A': 14.63,
    'B': 1.04,
    'C': 3.88,
    'D': 4.99,
    'E': 12.57,
    'F': 1.02,
    'G': 1.30,
    'H': 1.28,
    'I': 6.18,
    'J': 0.40,
    'K': 0.02,
    'L': 2.78,
    'M': 4.74,
    'N': 5.05,
    'O': 10.73,
    'P': 2.52,
    'Q': 1.20,
    'R': 6.53,
    'S': 7.81,
    'T': 4.34,
    'U': 4.63,
    'V': 1.67,
    'W': 0.01,
    'X': 0.21,
    'Y': 0.01,
    'Z': 0.47
}

frequencias = sorted(frequencias.keys(), key=lambda x: frequencias[x])
frequencias.reverse()
caracteres = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'

def afreq(string):
    str_freq = {}
    for c in string:
        if not c.isalnum():
            continue

        if c in str_freq:
            str_freq[c] += 1
        else:
            str_freq[c] = 1

    freq_sorted = sorted(str_freq.items(), key=lambda item: item[1])
    freq_sorted = [x[0] for x in freq_sorted]
    freq_sorted.reverse()
    most_freq = freq_sorted[0]

    possiveis_chaves = []

    for i, c in enumerate(frequencias):
        if c not in freq_sorted:
            continue

        index_c = caracteres.index(c)
        index_freq = caracteres.index(most_freq)

        possiveis_chaves.append((index_freq - index_c) % 26) # (indice da freq da letra na str - indice da letra em PT) % ignorar letras maiusculas

        print(freq_sorted[0], c + ' : ' + str(possiveis_chaves[-1]))

    return possiveis_chaves

file_str = open(sys.argv[1], 'r').read()
possiveis_chaves = afreq(file_str)

print(possiveis_chaves)

for key in possiveis_chaves:
    print(str(key) + ' : ' + cesar.cesar(file_str, -key))